Post #20

Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data (ICLR 2019) The paper proposes a DNN architecture, where each layer is a gradient boosting decision trees (GBDT) such that the outputs of previous layer are passed forward to the new one. A quite interesting contribution is how to make those GBDT layers differentiable for end-to-end training. https://arxiv.org/pdf/1909.06312.pdf